[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Muhammad Tanveer 1 ; Hung Khoon Tan 1 ; Hui Fuang Ng 1 ; Maylor Karhang Leung 1 and Joon Huang Chuah 2

Affiliations: 1 Faculty of Information and Communication Technology, Universiti Tunku Abdul Rahman, Malaysia ; 2 Faculty of Engineering, Universiti Malaya, Malaysia

Keyword(s): Batch Contrastive Loss, Batch Regularization, Center-level Contrastive Loss, Sample-level Contrastive Loss, Neural Network.

Abstract: As neural network becomes deeper, it becomes more capable of generating more powerful representation for a wide variety of tasks. However, deep neural network has a large number of parameters and easy to overfit the training samples. In this paper, we present a new regularization technique, called batch contrastive regularization. Regularization is performed by comparing samples collectively via contrastive loss which encourages intra-class compactness and inter-class separability in an embedded Euclidean space. To facilitate learning of embedding features for contrastive loss, a two-headed neural network architecture is used to decouple regularization classification. During inference, the regularization head is discarded and the network operates like any conventional classification network. We also introduce bag sampling to ensure sufficient positive samples for the classes in each batch. The performance of the proposed architecture is evaluated on CIFAR-10 and CIFAR-100 databases. Our experiments show that features regularized by contrastive loss has strong generalization performance, yielding over 8% improvement on ResNet50 for CIFAR-100 when trained from scratch. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 79.170.44.78

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Tanveer, M. ; Tan, H. ; Ng, H. ; Leung, M. and Chuah, J. (2020). Batch Contrastive Regularization for Deep Neural Network. In Proceedings of the 12th International Joint Conference on Computational Intelligence (IJCCI 2020) - NCTA; ISBN 978-989-758-475-6; ISSN 2184-3236, SciTePress, pages 368-377. DOI: 10.5220/0010135303680377

@conference{ncta20,
author={Muhammad Tanveer and Hung Khoon Tan and Hui Fuang Ng and Maylor Karhang Leung and Joon Huang Chuah},
title={Batch Contrastive Regularization for Deep Neural Network},
booktitle={Proceedings of the 12th International Joint Conference on Computational Intelligence (IJCCI 2020) - NCTA},
year={2020},
pages={368-377},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010135303680377},
isbn={978-989-758-475-6},
issn={2184-3236},
}

TY - CONF

JO - Proceedings of the 12th International Joint Conference on Computational Intelligence (IJCCI 2020) - NCTA
TI - Batch Contrastive Regularization for Deep Neural Network
SN - 978-989-758-475-6
IS - 2184-3236
AU - Tanveer, M.
AU - Tan, H.
AU - Ng, H.
AU - Leung, M.
AU - Chuah, J.
PY - 2020
SP - 368
EP - 377
DO - 10.5220/0010135303680377
PB - SciTePress

<style> #socialicons>a span { top: 0px; left: -100%; -webkit-transition: all 0.3s ease; -moz-transition: all 0.3s ease-in-out; -o-transition: all 0.3s ease-in-out; -ms-transition: all 0.3s ease-in-out; transition: all 0.3s ease-in-out;} #socialicons>ahover div{left: 0px;} </style>